metadata
base_model: facebook/vit-mae-base
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: MAE Model (model_idx_0584)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | MAE |
| Split | test |
| Base Model | facebook/vit-mae-base |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 0.0005 |
| LR Scheduler | constant_with_warmup |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 584 |
| Random Crop | True |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.4807 |
| Val Accuracy | 0.4069 |
| Test Accuracy | 0.4118 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
shrew, train, clock, rocket, bee, bottle, trout, streetcar, mouse, woman, house, pear, castle, couch, forest, chimpanzee, ray, leopard, sweet_pepper, motorcycle, mushroom, lawn_mower, girl, seal, elephant, cattle, lion, crab, bridge, bed, rabbit, possum, willow_tree, spider, plate, tractor, lamp, aquarium_fish, kangaroo, snail, flatfish, orchid, beaver, bowl, pine_tree, tulip, poppy, mountain, whale, lizard